Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging

Ayyoob Imani (1) , Silvia Severini (1) , Masoud Jalili Sabet (1) , François Yvon (2) , Hinrich Schütze (1)

1 LMU - Ludwig Maximilian University [Munich] = Ludwig Maximilians Universität München
2 TLP - Traitement du Langage Parlé - LISN

Part-of-Speech (POS) tagging is an important component of the NLP pipeline, but many lowresource languages lack labeled data for training. An established method for training a POS tagger in such a scenario is to create a labeled training set by transferring from high-resource languages. In this paper, we propose a novel method for transferring labels from multiple high-resource source to low-resource target languages. We formalize POS tag projection as graph-based label propagation. Given translations of a sentence in multiple languages, we create a graph with words as nodes and alignment links as edges by aligning words for all language pairs. We then propagate node labels from source to target using a Graph Neural Network augmented with transformer layers. We show that our propagation creates training sets that allow us to train POS taggers for a diverse set of languages. When combined with enhanced contextualized embeddings, our method achieves a new state-ofthe-art for unsupervised POS tagging of low resource languages.

Mots clés: Natural Language Processing; Cross-lingual Transfer; PoS-tagging

Mots clés: Traitement automatique des langues; Etiquetage en parties du discours; Transfert Cross-lingue

Domaines: Traitement du texte et du document

Ayyoob Imani, Silvia Severini, Masoud Jalili Sabet, François Yvon, Hinrich Schütze. Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging. Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Dec 2022, Abu Dhabi, United Arab Emirates. ⟨hal-03832874⟩